A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT

A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT (2008)

Cached

Download Links

[www.cs.cmu.edu]

by Andreas Zollmann , Ashish Venugopal , Franz Och , Jay Ponte , Google Inc

Venue:	In: Proceedings of ACL-COLING
Citations:	7 - 1 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT	INFERENCE
AUTHOR NAME	Andreas Zollmann	SVM HeaderParse 0.2
AUTHOR ADDR	1600 Amphitheatre Parkway; Mountain View, CA 94303, USA	SVM HeaderParse 0.2
AUTHOR NAME	Ashish Venugopal	SVM HeaderParse 0.2
AUTHOR ADDR	1600 Amphitheatre Parkway; Mountain View, CA 94303, USA	SVM HeaderParse 0.2
AUTHOR NAME	Franz Och	SVM HeaderParse 0.2
AUTHOR ADDR	1600 Amphitheatre Parkway; Mountain View, CA 94303, USA	SVM HeaderParse 0.2
AUTHOR NAME	Jay Ponte	SVM HeaderParse 0.2
AUTHOR ADDR	1600 Amphitheatre Parkway; Mountain View, CA 94303, USA	SVM HeaderParse 0.2
AUTHOR NAME	Google Inc	SVM HeaderParse 0.2
AUTHOR ADDR	1600 Amphitheatre Parkway; Mountain View, CA 94303, USA	SVM HeaderParse 0.2
ABSTRACT	Probabilistic synchronous context-free grammar (PSCFG) translation models define weighted transduction rules that represent translation and reordering operations via nonterminal symbols. In this work, we investigate the source of the improvements in translation quality reported when using two PSCFG translation models (hierarchical and syntax-augmented), when extending a state-of-the-art phrasebased baseline that serves as the lexical support for both PSCFG models. We isolate the impact on translation quality for several important design decisions in each model. We perform this comparison on three NIST language translation tasks; Chinese-to-English, Arabic-to-English and Urdu-to-English, each representing unique challenges. 1	SVM HeaderParse 0.2
YEAR	2008	INFERENCE
VENUE	In: Proceedings of ACL-COLING	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	1145--1152	INFERENCE
CITATIONS	17 found	ParsCit 1.0